kIieret/facebookresearch-ProgramBench
CLI tool
Can I trust it?
Worth a closer look before you use it.
Warnings Check
Very new: it was created 3 days ago. Wait a little before installing it.
Stars from real accounts No data
We haven't checked its stars for fakes yet.
Active OK
Last change 26 days ago.
Licence OK
MIT: you can use it for free, also in a commercial product. Keep the licence notice.
Quick checks from public data. They help, but they are no guarantee.
What it is
A benchmark that tests whether AI agents can rebuild a program from scratch. Given only a compiled binary and its documentation, agents must architect and implement a codebase that reproduces the original program's behavior. Provides a CLI, a leaderboard and a public dataset.
Who it's for
Researchers and developers evaluating coding agents and language models on software engineering tasks
How to use it
Install
uvx programbench --helpFrom its README. Check it there before running it.
Ask your AI to set it up
Paste this into Claude, ChatGPT or your coding assistant.
Help me install and set up kIieret/facebookresearch-ProgramBench in my project. Follow its README: https://github.com/kIieret/facebookresearch-ProgramBench. Explain each step and check it is safe before running anything.
Star curve
Get alerts for repos like this
We'll email you when something in AI agents starts rising. Free, once a week, only what matches.
What arrives: one email on Mondays with the repos that match, never more. See last week's. Privacy
For maintainers
Add this badge to your README. It shows the repo's place on the radar, updates every hour and links back to this page.
[](https://repoalerts.com/repo/kIieret/facebookresearch-ProgramBench?ref=badge)Similar repos
- facebookresearch/swe-sweep
A benchmark that measures how many bugs language models and agents can find and fix in large real repositories. Agents receive no hints about bug type or location. Tasks run on Harbor and are scored b
- kIieret/SWE-agent-SWE-agent
An agent framework in which a language model uses tools to work autonomously on GitHub issues in real repositories, and on other tasks such as offensive cybersecurity challenges (EnIGMA mode) and comp
- TIGER-AI-Lab/WebsiteBench
A benchmark in which AI agents explore a production website through a browser and must rebuild a full-stack version matching its appearance and behavior. Includes 70 websites and 46,916 hidden test ca
- aicodeking/leanrea
A single 8 KB agent skill file that gives AI coding agents routing rules and ready-to-run plain CLI commands for reverse engineering binaries, Electron apps and bundles, instead of an MCP server. It r
- Balanov/verdict
A 197 KB local classifier that reads a CLI tool call's command, exit code, stdout and stderr and labels the outcome as success, failure, blocked or unknown. Advisory only; it runs on CPU with no Pytho
- kingdee/lingee-bench
An evaluation framework and benchmark for testing whether AI agents complete tasks with verifiable outcomes in ERP-style business systems. It provides harness adapters, model and MCP proxies, an offli